AlignProp uses direct reward backpropogation for the alignment of large-scale text-to-image diffusion models. Our method is 25x more sample and compute efficient than reinforcement learning methods (PPO) for finetuning Stable Diffusion
☆328Nov 1, 2024Updated last year
Alternatives and similar repositories for AlignProp
Users that are interested in AlignProp are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- DDPO for finetuning diffusion models, implemented in PyTorch with LoRA support☆775Mar 22, 2024Updated 2 years ago
- Code for "Diffusion Model Alignment Using Direct Preference Optimization"☆715Jun 2, 2026Updated 4 months ago
- Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis☆679May 24, 2024Updated 2 years ago
- Code for the paper "Training Diffusion Models with Reinforcement Learning"☆578Jul 5, 2023Updated 3 years ago
- ☆605Dec 21, 2024Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- [NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences for Text-to-image Generation☆1,706Oct 29, 2025Updated 11 months ago
- Video Diffusion Alignment via Reward Gradients. We improve a variety of video diffusion models such as VideoCrafter, OpenSora, ModelScope…☆318Mar 12, 2025Updated last year
- [CVPR 2024] Code for the paper "Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model"☆244Apr 6, 2024Updated 2 years ago
- [NeurIPS 2024] 💫CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matching☆169Nov 18, 2024Updated last year
- [ICLR 2024 Spotlight] Official implementation of ScaleCrafter for higher-resolution visual generation at inference time.☆505Mar 7, 2024Updated 2 years ago
- [CVPR 2025] Aesthetic Post-Training Diffusion Models from Generic Preferences with Step-by-step Preference Optimization☆270Apr 7, 2025Updated last year
- [NeurIPS 2024] ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization☆167Sep 15, 2025Updated last year
- SEIKO is a novel reinforcement learning method to efficiently fine-tune diffusion models in an online setting. Our methods outperform all…☆31Jul 18, 2024Updated 2 years ago
- Better Aligning Text-to-Image Models with Human Preference. ICCV 2023☆291Jul 14, 2023Updated 3 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- The official repository of paper "ScaleLong: Towards More Stable Training of Diffusion Model via Scaling Network Long Skip Connection" (N…☆50Oct 23, 2023Updated 2 years ago
- CLIP+MLP Aesthetic Score Predictor☆1,349Jul 1, 2024Updated 2 years ago
- Diffusion Reinforcement Learning Library☆192Feb 13, 2024Updated 2 years ago
- [AAAI 2026] VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation☆427Mar 26, 2025Updated last year
- Official implementation of MARS: Mixture of Auto-Regressive Models for Fine-grained Text-to-image Synthesis☆86Jul 16, 2024Updated 2 years ago
- Official implementation of "Controlling Text-to-Image Diffusion by Orthogonal Finetuning".☆301Aug 29, 2025Updated last year
- RichHF-18K dataset contains rich human feedback labels we collected for our CVPR'24 paper: https://arxiv.org/pdf/2312.10240, along with t…☆157Jun 25, 2024Updated 2 years ago
- ☆74Jun 2, 2026Updated 4 months ago
- A one-stop library to standardize the inference and evaluation of all the conditional image generation models. [ICLR 2024]☆180Dec 2, 2025Updated 10 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis☆3,307Oct 31, 2024Updated last year
- PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator (NeurIPS 2024)☆537Sep 8, 2025Updated last year
- Consistency Distilled Diff VAE☆2,211Nov 7, 2023Updated 2 years ago
- Official codebase for Margin-aware Preference Optimization for Aligning Diffusion Models without Reference (MaPO).☆84Jun 11, 2024Updated 2 years ago
- [ICLR 2024] Code for FreeNoise based on VideoCrafter☆430Aug 25, 2025Updated last year
- Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation☆1,968Aug 15, 2024Updated 2 years ago
- Concept Sliders for Precise Control of Diffusion Models☆1,143Apr 13, 2026Updated 5 months ago
- Source code for "A Dense Reward View on Aligning Text-to-Image Diffusion with Preference" (ICML'24).☆38May 9, 2024Updated 2 years ago
- ELITE: Encoding Visual Concepts into Textual Embeddings for Customized Text-to-Image Generation (ICCV 2023, Oral)☆543Jan 8, 2024Updated 2 years ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- ☆509Jul 11, 2023Updated 3 years ago
- Official implementation of HPSv3: Towards Wide-Spectrum Human Preference Score (ICCV2025)☆364Dec 5, 2025Updated 10 months ago
- LLMScore: Unveiling the Power of Large Language Models in Text-to-Image Synthesis Evaluation☆135Oct 25, 2023Updated 2 years ago
- TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering☆192Apr 29, 2024Updated 2 years ago
- Official Pytorch Implementation of DenseDiffusion (ICCV 2023)☆508Nov 14, 2023Updated 2 years ago
- [ICLR 2024] Github Repo for "HyperHuman: Hyper-Realistic Human Generation with Latent Structural Diffusion"☆495Oct 14, 2023Updated 2 years ago
- FreeU: Free Lunch in Diffusion U-Net (CVPR2024 Oral)☆1,900Dec 24, 2024Updated last year